{"id":"https://openalex.org/W3204545020","doi":"https://doi.org/10.1109/spac53836.2021.9540001","title":"A Novel Reinforcement Learning Control for a class of Strict-feedback Discrete-time Systems via Multi-Gradient Recursive","display_name":"A Novel Reinforcement Learning Control for a class of Strict-feedback Discrete-time Systems via Multi-Gradient Recursive","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3204545020","doi":"https://doi.org/10.1109/spac53836.2021.9540001","mag":"3204545020"},"language":"en","primary_location":{"id":"doi:10.1109/spac53836.2021.9540001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spac53836.2021.9540001","pdf_url":null,"source":{"id":"https://openalex.org/S4306498851","display_name":"2021 International Conference on Security, Pattern Analysis, and Cybernetics\uff08SPAC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Security, Pattern Analysis, and Cybernetics\uff08SPAC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035160808","display_name":"Weiwei Bai","orcid":"https://orcid.org/0000-0002-1374-2228"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Bai","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025349097","display_name":"Tieshan Li","orcid":"https://orcid.org/0000-0003-0474-953X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieshan Li","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048027338","display_name":"Yue Long","orcid":"https://orcid.org/0000-0001-7843-400X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Long","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20554779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7949537038803101},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7485814094543457},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.727216362953186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5973709225654602},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5749157667160034},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.545275092124939},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5316515564918518},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.48730146884918213},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46591025590896606},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4613732099533081},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4195072054862976},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4150502681732178},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40952008962631226},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.374789834022522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33149099349975586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25364378094673157},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.15190157294273376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7949537038803101},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7485814094543457},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.727216362953186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5973709225654602},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5749157667160034},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.545275092124939},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5316515564918518},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.48730146884918213},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46591025590896606},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4613732099533081},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4195072054862976},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4150502681732178},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40952008962631226},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.374789834022522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33149099349975586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25364378094673157},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.15190157294273376},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spac53836.2021.9540001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spac53836.2021.9540001","pdf_url":null,"source":{"id":"https://openalex.org/S4306498851","display_name":"2021 International Conference on Security, Pattern Analysis, and Cybernetics\uff08SPAC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Security, Pattern Analysis, and Cybernetics\uff08SPAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3114554607","display_name":null,"funder_award_id":"61903092,51939001,61976033,61773187,U1813203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1849740853","https://openalex.org/W2089684487","https://openalex.org/W2107674817","https://openalex.org/W2117945258","https://openalex.org/W2141559645","https://openalex.org/W2142923542","https://openalex.org/W2162601317","https://openalex.org/W2765545170","https://openalex.org/W3003040443"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W1990502710","https://openalex.org/W2159479095"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,34,62,66,72,79,87,94,101,107,113,127],"reinforcement":[4],"learning":[5,70,78],"control":[6,25,38,114],"design":[7],"problem":[8,90],"via":[9],"multi-gradient":[10],"recursive":[11],"(MGR)":[12],"for":[13],"a":[14,49],"general":[15,32],"class":[16],"of":[17,103],"strict":[18],"feedback":[19],"systems.":[20],"The":[21,40],"system":[22,115],"with":[23,36],"unknown":[24,63],"gain":[26],"is":[27,30,45,58,75],"studied,":[28],"which":[29,82],"more":[31],"than":[33],"one":[35],"known":[37],"gain.":[39],"long-term":[41],"strategic":[42],"utility":[43],"function":[44,64],"estimated":[46],"by":[47],"constructing":[48],"critic":[50],"neural":[51],"network":[52],"(NN),":[53],"and":[54],"an":[55],"actuator":[56],"NN":[57],"constructed":[59],"to":[60,77,106,118,133],"estimate":[61],"in":[65,93,112],"controller.":[67],"A":[68],"novel":[69],"strategy,":[71],"socalled":[73],"MGR,":[74],"proposed":[76],"weight":[80],"vector,":[81],"can":[83],"not":[84],"only":[85],"eliminate":[86],"local":[88],"optimal":[89],"that":[91],"inherent":[92],"gradient":[95],"descent":[96],"method":[97],"but":[98],"also":[99],"improve":[100],"rate":[102],"convergency.":[104],"According":[105],"Lyapunov":[108],"theory,":[109],"all":[110],"signals":[111],"are":[116,131],"ensured":[117],"be":[119],"semiglobal":[120],"uniformly":[121],"ultimately":[122],"bounded":[123],"(SGUUB).":[124],"At":[125],"last,":[126],"comparison":[128],"simulation":[129],"examples":[130],"given":[132],"validate":[134],"this":[135],"strategy.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}